Papers by Guodong Zhou

Low-Resource Comparative Opinion Quintuple Extraction by Data Augmentation with Prompting (2023.findings-emnlp)

Challenge:	Existing studies on depression detection rely on textual and visual content to determine whether a human being is depressed or non-depressed.
Approach:	They propose a multimodal topic-enriched Auxiliary Learning approach that captures topic information from texts and images for depression detection.
Outcome:	The proposed approach improves the performance of the primary task by using topic information from text and images.

Copied to clipboard

Qingting Xu, Yu Hong, Fubang Zhao, Kaisong Song, Yangyang Kang, Jiaxiang Chen, Guodong Zhou

Low-Resource NLP

Challenge:	Comparative Opinion Quintuple Extraction (COQE) aims to predict comparative opinion quintuples from comparative sentences.
Approach:	They propose a low-resource approach to extract comparative opinion quintuples from comparative sentences . they propose augmentation using ChatGPT and a data-centric approach .
Outcome:	The proposed approach improves the existing pipeline-based method and achieves state-of-the-art results.

How to Understand “Support”? An Implicit-enhanced Causal Inference Approach for Weakly-supervised Phrase Grounding (2024.lrec-main)

Copied to clipboard

Jiamin Luo, Jianing Zhao, Jingjing Wang, Guodong Zhou

Cross-domain NER with Generated Task-Oriented Knowledge: An Empirical Study from Information Density Perspective (2024.emnlp-main)

Challenge:	Existing studies on Weakly-supervised Phrase Grounding (WPG) largely ignore the implicit phrase-region matching relations, rendering it arduous to explore the semantic nature of phrases.
Approach:	They propose an Implicit-Enhanced Causal Inference approach to address the challenges of modeling the implicit relations and highlighting them beyond the explicit.
Outcome:	The proposed approach outperforms the state-of-the-art baselines on an implicit-enhanced dataset.

Copied to clipboard

Zhihao Zhang, Sophia Lee, Junshuang Wu, Dong Zhang, Shoushan Li, Erik Cambria, Guodong Zhou

Negative Focus Detection via Contextual Attention Mechanism (D19-1)

Challenge:	Cross-domain Named Entity Recognition (CDNER) is crucial for Knowledge Graph (KG) construction and natural language processing (NLP)
Approach:	They propose to automatically generate task-oriented knowledge using large language models (LLMs) and then employ task-orientated pre-training (TOPT) to facilitate domain adaptation.
Outcome:	The proposed model can learn to distinguish between different entities and improve its domain adaptation.

Copied to clipboard

Longxiang Shen, Bowei Zou, Yu Hong, Guodong Zhou, Qiaoming Zhu, AiTi Aw

Challenge:	Negation is a universal but complicated linguistic phenomenon that reverses the polarity of a statement or its property into opposite.
Approach:	They propose a framework which consists of a Bidirectional Long Short-Term Memory neural network and a Conditional Random Fields layer to capture contextual information.
Outcome:	The proposed framework improves on the SEM’12 shared task corpus, yielding an absolute improvement of 2.11% over the state-of-the-art.

Exploring Knowledge Filtering for Retrieval-Augmented Discriminative Tasks (2025.findings-acl)

Copied to clipboard

Minjie Qiang, Zhongqing Wang, Xiaoyi Bao, HaoYuan Ma, Shoushan Li, Guodong Zhou

Joint Multi-modal Aspect-Sentiment Analysis with Auxiliary Cross-modal Relation Detection (2021.emnlp-main)

Challenge:	Recent studies have focused on generative tasks, while its potential in discriminative tasks remains largely unexplored.
Approach:	They propose a framework that incorporates knowledge filtering and prediction fusion mechanisms to improve model performance.
Outcome:	The proposed framework improves model performance on discriminative tasks by filtering out harmful knowledge and integrating it into the input context.

Copied to clipboard

Xincheng Ju, Dong Zhang, Rong Xiao, Junhui Li, Shoushan Li, Min Zhang, Guodong Zhou

A Top-down Neural Architecture towards Text-level Parsing of Discourse Rhetorical Structure (2020.acl-main)

Challenge:	Existing studies on aspect-level sentiment analysis focus on extracting aspect terms and sentiment polarities separately.
Approach:	They propose a multi-modal joint learning approach with auxiliary cross-modal relation detection for multi-dimensional aspect-level sentiment analysis.
Outcome:	The proposed approach can obtain all aspect-level sentiment polarities dependent on the jointly extracted specific aspects.

Copied to clipboard

Longyin Zhang, Yuqing Xing, Fang Kong, Peifeng Li, Guodong Zhou

Modeling Graph Structure in Transformer for Better AMR-to-Text Generation (D19-1)

Challenge:	Text-level discourse parsing of discourse rhetorical structure (DRS) is a fundamental research topic in natural language processing.
Approach:	They propose a top-down neural architecture for text-level discourse parsing . they cast the parser as a recursive split point ranking task .
Outcome:	The proposed top-down approach is more suitable for text-level discourse parsing.

Copied to clipboard

Jie Zhu, Junhui Li, Muhua Zhu, Longhua Qian, Min Zhang, Guodong Zhou

Hierarchical Modeling of Global Context for Document-Level Neural Machine Translation (D19-1)

Challenge:	Recent studies on AMR-to-text generation formalize the task as a sequence-tosequence learning problem . previous approaches only consider the relations between directly connected concepts while ignoring the rich structure in AMR graphs.
Approach:	They propose a structure-aware self-attention approach to model the relations between indirectly connected concepts in the seq2seq model.
Outcome:	The proposed approach outperforms the state-of-the-art on English AMR benchmarks . it significantly outperformed the state of the art on the benchmarks, with 29.66 and 31.82 BLEU scores .

Copied to clipboard

Xin Tan, Longyin Zhang, Deyi Xiong, Guodong Zhou

Text Generation

Challenge:	Document-level machine translation (MT) remains challenging due to the difficulty in efficiently using document context.
Approach:	They propose a hierarchical model to learn document context for document-level neural machine translation . they use a sentence encoder to capture intra-sentence dependencies and a document encoder .
Outcome:	The proposed model significantly improves document-level translation performance over strong baselines.

NUT-RC: Noisy User-generated Text-oriented Reading Comprehension (2020.coling-main)

Copied to clipboard

Rongtao Huang, Bowei Zou, Yu Hong, Wei Zhang, AiTi Aw, Guodong Zhou

Reasoning

Challenge:	Existing RC models focus on extractive or generative, but ignore integration of them.
Approach:	They propose a noisy user-generated text-oriented RC model that integrates extractive and generative RC models by a multi-task learning mechanism and an answer selection module.
Outcome:	The proposed model outperforms state-of-the-art models on Twitter.

A Unified Framework for Synaesthesia Analysis (2023.findings-emnlp)

Copied to clipboard

Kun Sheng, Zhongqing Wang, Qingqing Zhao, Xiaotong Jiang, Guodong Zhou

Cognitive Modeling

Challenge:	Synaesthesia is a cognitive phenomenon structuring human thought and action, which makes understanding it challenging.
Approach:	They propose a framework for annotating synaesthetic elements and exploring their relationship . they propose to include sensory modalities, cues and stimuli in the framework .
Outcome:	The proposed framework yields state-of-the-art results, demonstrating its effectiveness.

Unregulated Chinese-to-English Data Expansion Does NOT Work for Neural Event Detection (2022.coling-1)

Copied to clipboard

Zhongqiu Li, Yu Hong, Jie Wang, Shiming He, Jianmin Yao, Guodong Zhou

Adversarial Learning for Discourse Rhetorical Structure Parsing (2021.acl-long)

Challenge:	Experimental results show that cross-language data expansion results in performance degradation.
Approach:	They leverage cross-language data expansion and retraining to enhance neural Event Detection on English ACE corpus.
Outcome:	The proposed method improves ED performance by 1.6% over the straight data combination.

Copied to clipboard

Longyin Zhang, Fang Kong, Guodong Zhou

Document-Level Event Factuality Identification via Adversarial Neural Network (N19-1)

Challenge:	Existing top-down discourse rhetorical structure parsers make local decisions and ignore global parsing.
Approach:	They propose a method to transform gold standard and predicted constituency trees into tree diagrams with two color channels.
Outcome:	The proposed method improves performance on RST-DT and CDTB corpora and can leverage global context.

Copied to clipboard

Zhong Qian, Peifeng Li, Qiaoming Zhu, Guodong Zhou

Using active learning to expand training data for implicit discourse relation recognition (D18-1)

Challenge:	Document-level event factuality identification is crucial for discourse understanding in NLP . identifying document-level factual of events requires comprehensive understanding of documents .
Approach:	They propose to construct a corpus annotated with document- and sentence-level event factuality information on English and Chinese texts.
Outcome:	The proposed model outperforms baselines on the constructed corpus.

Copied to clipboard

Yang Xu, Yu Hong, Huibin Ruan, Jianmin Yao, Min Zhang, Guodong Zhou

Responsible & Trustworthy NLP

Challenge:	Existing methods to determine semantic relations between text spans are limited in the field of discourse-level relation recognition.
Approach:	They propose to expand the training data set using the corpus of explicitly-related arguments by arbitrarily dropping the overtly presented discourse connectives.
Outcome:	The proposed model expands the training data set using the corpus of explicitly-related arguments, by arbitrarily dropping the overtly presented discourse connectives.

EDTC: A Corpus for Discourse-Level Topic Chain Parsing (2021.findings-emnlp)

Copied to clipboard

Longyin Zhang, Xin Tan, Fang Kong, Guodong Zhou

Discourse & Pragmatics

Challenge:	Discourse analysis is a fundamental part of natural language processing.
Approach:	They propose a discourse-level topic chain parsing system which can be automated . they propose lexical cohesion modeling instead of lexically measuring topic structure .
Outcome:	The proposed system is robust and reliable, and can provide high reliability and low confidence scores.

Aspect-based Sentiment Analysis via Synthetic Image Generation (2025.findings-emnlp)

Copied to clipboard

Ge Chen, Zhongqing Wang, Guodong Zhou

Don’t Just Listen, Try Planning: Graph-based Retrieval-Generation Agent for Long-form Audio Meeting Understanding (2026.findings-acl)

Challenge:	Recent advances in Aspect-Based Sentiment Analysis (ABSA) have shown promising results, yet the semantics derived solely from textual data remain limited.
Approach:	They propose a supervised image generation framework to generate synthetic images with alignment to text and sentiment information.
Outcome:	The proposed approach significantly outperforms state-of-the-art methods on multiple benchmark datasets.

Copied to clipboard

Quanwei Tang, Dong Zhang, Shoushan Li, Guodong Zhou

S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA (2026.acl-long)

Challenge:	Existing question answering (QA) datasets for long audio meetings suffer from acoustic information loss and poor long-term dependency capture.
Approach:	They propose a question answering dataset that captures three core dimensions of long-form audio meeting content.
Outcome:	The proposed model captures three core dimensions of long-form audio meeting content: complex semantics, multi-speaker interactions, and quite long timestamps.

Copied to clipboard

Minghan Li, Junjie Zou, Xinxuan Lv, Chao Zhang, Guodong Zhou

Question Answering

Challenge:	Retrieval-augmented generation grounds language models in external evidence, but multi-hop question answering remains difficult . iterative pipelines must control what to retrieve next and when evidence is adequate.
Approach:	They propose an iterative framework with an explicit controller, S2G-Judge . they map structured gap items into the next retrieval query to produce stable retrieval trajectories .
Outcome:	Experiments on TriviaQA, HotpotQA, and 2WikiMultiHopQA show that S2G-RAG improves multi-hop QA performance and robustness under multi-turn retrieval.

Improving Cross-modal Alignment for Text-Guided Image Inpainting (2023.eacl-main)

Copied to clipboard

Yucheng Zhou, Guodong Long

Visual Data in NLP

Challenge:	Existing methods allocate most of computation to visual encoding, while light computation on modeling modality interactions.
Approach:	They propose a novel model for text-guided image inpainting by improving cross-modal alignment knowledge by using a vision-language encoder and an image generator.
Outcome:	The proposed model achieves state-of-the-art performance compared with other strong competitors on two vision-language datasets.

Employing Text Matching Network to Recognise Nuclearity in Chinese Discourse (C18-1)

Copied to clipboard

Sheng Xu, Peifeng Li, Guodong Zhou, Qiaoming Zhu

Challenge:	Experimental results show that nuclearity recognition is a challenging task in Chinese discourse parsing due to the need for more deep semantic information.
Approach:	They propose a text matching network that encodes discourse units and paragraphs by combining Bi-LSTM and CNN to capture global dependency information and local n-gram information.
Outcome:	The proposed model outperforms baselines on the Chinese Discourse TreeBank . the proposed model is based on a novel text matching network .

Transition-based Opinion Generation for Aspect-based Sentiment Analysis (2024.findings-acl)

Copied to clipboard

Tianlai Ma, Zhongqing Wang, Guodong Zhou

Modeling Coherence for Neural Machine Translation with Dynamic and Topic Caches (C18-1)

Challenge:	Existing approaches to aspect-based sentiment analysis often overlook the importance of explicitly modeling structure among sentiment elements.
Approach:	They propose to integrate general pre-trained sequence-to-sequence language models with a structure-aware transition-based approach to model sentiment structure.
Outcome:	The proposed model improves the state-of-the-art performance on several benchmark datasets.

Copied to clipboard

Shaohui Kuang, Deyi Xiong, Weihua Luo, Guodong Zhou

Breaking the Corpus Bottleneck for Context-Aware Neural Machine Translation with Cross-Task Pre-training (2021.acl-long)

Challenge:	Current neural machine translation systems translate a text sentence-by-sentence, ignoring cross-sentent links and dependencies.
Approach:	They propose a cache-based approach to modeling coherence for neural machine translation . they capture contextual information either from recently translated sentences or the entire document .
Outcome:	The proposed model improves on state-of-the-art translation models on many languages . it captures contextual information from recently translated sentences or the entire document .

Copied to clipboard

Linqing Chen, Junhui Li, Zhengxian Gong, Boxing Chen, Weihua Luo, Min Zhang, Guodong Zhou

Machine Translation

Challenge:	Context-aware neural machine translation (NMT) remains challenging due to the lack of large-scale document-level parallel corpora.
Approach:	They propose to use large-scale parallel datasets and source-side monolingual documents to improve context-aware neural machine translation.
Outcome:	The proposed model can be used to translate both sentences and documents on four translation tasks.

Multimodal Event Transformer for Image-guided Story Ending Generation (2023.eacl-main)

Copied to clipboard

Yucheng Zhou, Guodong Long

Exploring Graph Pre-training for Aspect-based Sentiment Analysis (2023.findings-emnlp)

Challenge:	Existing methods focus on cross-modal feature fusion but overlook reasoning and mining implicit information from story plots and ending image.
Approach:	They propose a multimodal event transformer framework for image-guided story ending generation.
Outcome:	The proposed method achieves state-of-the-art performance for image-guided story ending generation.

Copied to clipboard

Xiaoyi Bao, Zhongqing Wang, Guodong Zhou

Taking Actions Separately: A Bidirectionally-Adaptive Transfer Learning Method for Low-Resource Neural Machine Translation (2022.coling-1)

Challenge:	Existing studies tend to extract the sentiment elements in a generative manner to avoid complex modeling of sentiment elements.
Approach:	They propose a generative model with an Element-level Graph Pre-training paradigm and a Task Decomposition Pre- training paradigm to make it generalizable and robust against irregular sentiment quadruples.
Outcome:	The proposed model is generalizable and robust against irregular sentiment quadruples.

Copied to clipboard

Xiaolin Xing, Yu Hong, Minhan Xu, Jianmin Yao, Guodong Zhou

Structure-aware Generation Model for Cross-Domain Aspect-based Sentiment Classification (2024.lrec-main)

Challenge:	Existing approaches to train NMT models rely on sparse parallel data . a variety of PC variants yield significant improvements for low-resource NMT .
Approach:	They propose to transfer well-trained NMT models to low-resource languages by bidirectionally-adaptive learning strategy . they divide inner constituents of Parent encoder into two "teams" aiming to adapt to characteristics of low- and high-resourced languages .
Outcome:	The proposed method improves on low-resource NMT models with a variety of PC variants.

Copied to clipboard

Shichen Li, Zhongqing Wang, Yanzhi Xu, Guodong Zhou

End-to-End Emotion Semantic Parsing (2024.findings-acl)

Challenge:	Existing generation models for cross-domain aspect-based sentiment classification ignore syntactic structures . syntaktic structures are pre-trained on natural language and can be catastrophic forgetting of distributional knowledge.
Approach:	They propose a structure-aware generation model that explicitly encodes syntactic structure into the model.
Outcome:	The proposed model can learn domain-irrelevant features based on syntactic pivot features.

Copied to clipboard

Xiaotong Jiang, Zhongqing Wang, Guodong Zhou

MCDTB: A Macro-level Chinese Discourse TreeBank (C18-1)

Challenge:	Existing studies focus on detecting emotion from text, but recent studies have shown that emotions may be experienced and caused by semantic constituents.
Approach:	They propose a task called emotion semantic parsing which parses emotion and semantic constituents into an abstract semantic tree structure.
Outcome:	The proposed model performs better than existing models and is more cognitive and structurally robust.

Copied to clipboard

Feng Jiang, Sheng Xu, Xiaomin Chu, Peifeng Li, Qiaoming Zhu, Guodong Zhou

Syntactic Text Processing

Challenge:	Discourse analysis is becoming increasingly important in the field of natural language processing.
Approach:	They propose to annotate macro discourse information and additional discourse information to make annotation more objective and accurate.
Outcome:	The results show that the annotations are more objective and accurate than the previous ones.

Document-level Event Factuality Identification via Machine Reading Comprehension Frameworks with Transfer Learning (2022.coling-1)

Copied to clipboard

Zhong Qian, Heng Zhang, Peifeng Li, Qiaoming Zhu, Guodong Zhou

Semantic Simplification for Sentiment Classification (2022.emnlp-main)

Challenge:	Document-level Event Factuality Identification (DEFI) is a fundamental and crucial task in NLP.
Approach:	They propose a framework for document-level event factuality identification (DEFI) they propose to use Span-Extraction and Multiple-Choice to model DEFI as machine reading comprehension tasks .
Outcome:	The proposed model outperforms state-of-the-art models on a document-based event factuality task . it uses Span-Extraction (Ext) and Multiple-Choice (Mch) knowledge to extract knowledge from large-scale MRC corpus .

Copied to clipboard

Xiaotong Jiang, Zhongqing Wang, Guodong Zhou

ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification (2022.acl-long)

Challenge:	Recent work on document-level sentiment classification has shown that the sentiment in the original text is often hard to capture . previous studies focus on predicting the overall sentiment from original text using statistical or neural models, but these methods either heavily rely on human knowledge or suffer from the complex structure of the text.
Approach:	They propose a document-level sentiment classification model that enhances the original text with a simplified clause to intensify its sentiment.
Outcome:	Empirical studies show that the proposed model over strong baselines is effective over several strong baseline models.

Copied to clipboard

Yucheng Zhou, Tao Shen, Xiubo Geng, Guodong Long, Daxin Jiang

Opinion Tree Parsing for Aspect-based Sentiment Analysis (2023.findings-acl)

Challenge:	Existing work on event-centric reasoning fails to model event-level correlations . Existing studies limit their scope to specific scenarios or overlook event- level correlations.
Approach:	They propose to pre-train a general Correlation-aware context-to-Event Transformer for event-centric reasoning by highlighting event-level correlations with effective training.
Outcome:	The proposed model is applicable to a wide range of event-centric reasoning scenarios, considering its versatility of event correlation types, application formulations, and reasoning types.

Copied to clipboard

Xiaoyi Bao, Xiaotong Jiang, Zhongqing Wang, Yue Zhang, Guodong Zhou

Incorporating Image Matching Into Knowledge Acquisition for Event-Oriented Relation Recognition (C18-1)

Challenge:	Existing generative models for aspect-based sentiment analysis lack structure well-formedness guarantees and built-in elements alignments.
Approach:	They propose an opinion tree parsing model which parses all sentiment elements from an opinion-tree.
Outcome:	The proposed model is much faster than previous models and can explore correlations among sentiment elements.

Copied to clipboard

Yu Hong, Yang Xu, Huibin Ruan, Bowei Zou, Jianmin Yao, Guodong Zhou

Visual Data in NLP

Challenge:	Event relation recognition is a challenging language processing task because the query events are selected from different paragraphs in a document or even different documents, so there is lack of explicit clue.
Approach:	They propose to use image processing to acquire similar event instances and use image matching to approximate calculation between events.
Outcome:	The proposed model performs comparable to CNN while slightly better than LSTM on the ACE-R2 corpus.

Pre-trained Token-replaced Detection Model as Few-shot Learner (2022.coling-1)

Copied to clipboard

Zicheng Li, Shoushan Li, Guodong Zhou

Sentiment Forecasting in Dialog (2020.coling-main)

Challenge:	Pre-trained masked language models have demonstrated remarkable few-shot learning ability . a novel approach to few- shot learning with pre-tried token-replaced detection models is proposed .
Approach:	They propose a method to reformulate a classification or regression task as a token-replaced detection problem by using pre-trained token-based models.
Outcome:	The proposed approach outperforms pre-trained masked language models in learning tasks . it can learn models with a few examples and generalize well from limited examples like humans .

Copied to clipboard

Zhongqing Wang, Xiujun Zhu, Yue Zhang, Shoushan Li, Guodong Zhou

Dialogue Systems & Conversational Agents

Challenge:	Existing studies on sentiment classification focus on determining polarity of existing utterances.
Approach:	They propose a Neural Sentiment Forecasting task which simulates the next utterance based on context and a sequence influence model to learn both pair-wise and seq-wise influence.
Outcome:	The proposed model outperforms existing models over several strong baselines.

Exploring Multilingual Pre-trained Language Model for Aspect-based Sentiment Analysis (2026.findings-acl)

Copied to clipboard

Ye Wang, Ruijun Jiang, Zhongqing Wang, Guodong Zhou

Using Subtext to Enhance Generative IDRR (2025.acl-short)

Challenge:	Aspect-based sentiment analysis studies have focused on English datasets, but labeled data is scarce.
Approach:	They propose a multilingual pre-trained language model that leverages bilingual pre-training to leverage aspects-based sentiment analysis.
Outcome:	The proposed model outperforms state-of-the-art models across multiple languages.

Copied to clipboard

Zhipang Wang, Yu Hong, Weihao Sun, Guodong Zhou

Exploring Artificial Image Generation for Stance Detection (2025.emnlp-main)

Challenge:	Arguments contain subtexts, but they are connotative and need prompts to be recognized . a lightweight subtext generator is helpful when the prompt doesn't raise a complex CoT.
Approach:	They leverage LLaMA to generate subtexts for argument pairs and verify their effectiveness . they construct a baseline IDRR using the decoder-only backbone LLama .
Outcome:	The proposed approach achieves higher F1 scores on two benchmarks than previous models.

Copied to clipboard

Zhengkang Zhang, Zhongqing Wang, Guodong Zhou

A Comprehensive Graph Framework for Question Answering with Mode-Seeking Preference Alignment (2025.findings-acl)

Challenge:	Existing approaches to stance detection focus on textual content, which may not capture the implicit stance conveyed by the author.
Approach:	They propose a novel approach that transforms original texts into artificially generated images and uses the visual representation to enhance stance detection.
Outcome:	The proposed model is able to detect author's stance from a set of artificially generated images and then leverages both the original textual content and the generated image to identify the author' stance.

Copied to clipboard

Quanwei Tang, Sophia Yat Mei Lee, Junshuang Wu, Dong Zhang, Shoushan Li, Erik Cambria, Guodong Zhou

Structured Data in NLP

Challenge:	Existing studies struggle with achieving global understanding of large language models . GraphMPA is a graph-based framework with mode-seeking preference alignment .
Approach:	They propose a graph-based framework with mode-seeking preference alignment to improve model outputs.
Outcome:	The proposed framework constructs a hierarchical document graph mimicking human cognitive processes for information understanding and synthesis.

Adversarial Feature Adaptation for Cross-lingual Relation Classification (C18-1)

Copied to clipboard

Bowei Zou, Zengzhuang Xu, Yu Hong, Guodong Zhou

Emotion Detection with Neural Personal Discrimination (D19-1)

Challenge:	Existing methods for relation classification exploit monolingual data due to lack of annotated data in other languages.
Approach:	They propose an adversarial feature adaptation approach for cross-lingual relation classification using a generative adversarial network.
Outcome:	The proposed approach yields an improvement of 5.7% over the state-of-the-art.

Copied to clipboard

Xiabing Zhou, Zhongqing Wang, Shoushan Li, Guodong Zhou, Min Zhang

Aspect Sentiment Classification with Document-level Sentiment Preference Modeling (2020.acl-main)

Challenge:	Existing approaches to automatically predict the emotions of posts consider each post individually and predict their emotions independently.
Approach:	They propose a Neural Personal Discrimination approach to identify personal attributes from posts and connect relevant posts with similar attributes to jointly learn their emotions.
Outcome:	The proposed approach improves on existing models by capturing attributes-aware words and predicting emotions among relevant posts.

Copied to clipboard

Xiao Chen, Changlong Sun, Jingjing Wang, Shoushan Li, Luo Si, Min Zhang, Guodong Zhou

Danger Depends on the Mind: A Theory-of-Mind Grounded Dataset and Model for Context-Dependent Dangerous Speech (2026.findings-acl)

Challenge:	Existing studies consider Aspect Sentiment Classification (ASC) as an independent sentence-level classification problem aspect by aspect.
Approach:	They propose a Cooperative Graph Attention Networks approach for cooperatively learning aspect-related sentence representation.
Outcome:	The proposed approach outperforms the state-of-the-art methods in document-level sentiment classification.

Copied to clipboard

Yuanchen Shi, Longyin Zhang, Guodong Zhou, Fang Kong

Demonstration Retrieval-Augmented Generative Event Argument Extraction (2024.lrec-main)

Challenge:	Existing methods for dangerous speech detection rely on binary labels that ignore who is speaking and in what mental state.
Approach:	They propose a context-dependent variant of dangerous speech detection by grounding it in Theory-of-Mind.
Outcome:	The proposed model outperforms proprietary and open-source models with significantly fewer parameters.

Copied to clipboard

Shiming He, Yu Hong, Shuai Yang, Jianmin Yao, Guodong Zhou

Low-Resource NLP

Challenge:	Experimental results show that our method outperforms all strong baselines and can be generalized to various datasets.
Approach:	They propose a generative EAE that uses event knowledge-injected generator and demonstration retriever to generate event arguments from training data.
Outcome:	The proposed method outperforms baselines and can be generalized to various datasets.

Leveraging AMR Graph Structure for Better Sequence-to-Sequence AMR Parsing (2024.lrec-main)

Copied to clipboard

Linyu Fan, Wu Wu Yiheng, Jun Xie, Junhui Li, Fang Kong, Guodong Zhou

Zero-shot Cross-lingual NER via Mitigating Language Difference: An Entity-aligned Translation Perspective (2025.findings-emnlp)

Challenge:	Recent studies on AMR parsing often regard this task as a seq2seq translation problem.
Approach:	They propose to translate AMR graphs into AMR token sequences in pre-processing and recover AMR from sequences after decoding.
Outcome:	The proposed approach outperforms baseline and achieves 85.5 0.1 and 84.2 0.2 Smatch scores on AMR 2.0 and AMR 3.0.

Copied to clipboard

Zhihao Zhang, Sophia Yat Mei Lee, Dong Zhang, Shoushan Li, Guodong Zhou

Topic Tensor Network for Implicit Discourse Relation Recognition in Chinese (P19-1)

Challenge:	Existing approaches to cross-lingual Named Entity Recognition focus on Latin script language (LSL) for non-Latin script language, performance often degrades due to deep structural differences.
Approach:	They propose an entity-aligned translation approach to align entities between NSL and English .
Outcome:	The proposed approach aims to transfer knowledge from high-resource languages to low-resourced languages.

Copied to clipboard

Sheng Xu, Peifeng Li, Fang Kong, Qiaoming Zhu, Guodong Zhou

Challenge:	Currently, most studies on implicit discourse relation recognition use sentence-level representations . Chinese is a paratactic language that tends to pro-drop clause connectives .
Approach:	They propose a topic tensor network to recognize Chinese implicit discourse relations with both sentence-level and topic-level representations.
Outcome:	The proposed model outperforms state-of-the-art models in micro and macro F1 scores on a Chinese discourse corpus.

ChatASU: Evoking LLM’s Reflexion to Truly Understand Aspect Sentiment in Dialogues (2024.lrec-main)

Copied to clipboard

Yiding Liu, Jingjing Wang, Jiamin Luo, Tao Zeng, Guodong Zhou

Natural Language Interfaces

Challenge:	Existing studies on interactive ASU ignore the coreference issue for opinion targets while this phenomenon is ubiquitous in interactive scenarios especially dialogues, limiting the ASU performance.
Approach:	They propose a Chat-based Aspect Sentiment Understanding task that integrates various NLP tasks with the chat paradigm and propose 'trusted self-reflexion' approach with ChatGLM as backbone to address aspect coreference issue.
Outcome:	The proposed task outperforms state-of-the-art baselines and shows that it is highly effective.

Bridging Modality Gap for Effective Multimodal Sentiment Analysis in Fashion-related Social Media (2025.coling-main)

Copied to clipboard

Zheyu Zhao, Zhongqing Wang, Shichen Li, Hongling Wang, Guodong Zhou

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks (2026.findings-acl)

Challenge:	Existing sentiment analysis tasks focus on text comprehension, but visual content is important for emotional expression.
Approach:	They propose a multimodal framework that integrates information from various modalities for sentiment classification of fashion posts.
Outcome:	The proposed framework outperforms existing unimodal and multimodal baselines on a comprehensive dataset and significantly outperformed existing unilmodal and multiple modal frameworks.

Copied to clipboard

Zhuo Li, Guodong DU, Zesheng Shi, Weiyang Guo, Weijun Yao, Yuan Zhou, Jiabo Zhang, Jing Li

Green & Sustainable NLP

Challenge:	Large Language Models (LLMs) can specialize under fixed memory and inference budgets, but they struggle to achieve high performance across heterogeneous domains.
Approach:	They propose a modular improvement framework that partitions full capabilities of a general-purpose model into domain-specific delta modules that reorganize and refine the model's internal knowledge.
Outcome:	The proposed framework outperforms monolithic models on multi-task and agentic benchmarks and achieves up to 4 speedup.

Improving Long-Tail Relation Extraction with Collaborating Relation-Augmented Attention (2020.coling-main)

Copied to clipboard

Yang Li, Tao Shen, Guodong Long, Jing Jiang, Tianyi Zhou, Chengqi Zhang

Self-regulation: Employing a Generative Adversarial Network to Improve Event Detection (P18-1)

Challenge:	Existing approaches to handle wrong labeling and long-tail relations are labor-intensive and scarce training data.
Approach:	They propose a neural network to handle wrong labeling and long-tail relations by collaborating relation-augmented attention.
Outcome:	The proposed neural network improves the state-of-the-art on the NYT dataset .

Copied to clipboard

Yu Hong, Wenxuan Zhou, Jingli Zhang, Guodong Zhou, Qiaoming Zhu

Tensorized Self-Attention: Efficiently Modeling Pairwise and Global Dependencies Together (N19-1)

Challenge:	Recent studies show that neural networks can be used for event detection but can be contaminated by spurious features.
Approach:	They propose a self-regulated learning approach by utilizing a generative adversarial network to generate spurious features.
Outcome:	The proposed method is highly effective and adaptable on the ACE 2005 and TAC-KBP 2015 corpora.

Copied to clipboard

Tao Shen, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang

One vs. Many QA Matching with both Word-level and Sentence-level Attention Network (C18-1)

Challenge:	Neural networks equipped with self-attention have parallelizable computation and the ability to capture both long-range and local dependencies.
Approach:	They propose a novel attention mechanism called "Multi-mask Tensorized Self-Attention" it captures pairwise and global dependencies by a compatibility function composed of dot-product and additive attentions .
Outcome:	The proposed model outperforms CNN-/RNN-/attention-based models on nine NLP benchmarks with compelling memory- and time-efficiency.

Copied to clipboard

Lu Wang, Shoushan Li, Changlong Sun, Luo Si, Xiaozhong Liu, Min Zhang, Guodong Zhou

Question Answering

Challenge:	Existing studies on question answer matching focus on formal text . however, there exists many scenarios where the QA text is informal .
Approach:	They propose a novel QA matching approach using informal text from a product review site.
Outcome:	The proposed approach improves word-level and sentence-level attentions for solving the noisy problem in the informal text.

Cross-Domain Sentiment Classification using Semantic Representation (2022.findings-emnlp)

Copied to clipboard

Shichen Li, Zhongqing Wang, Xiaotong Jiang, Guodong Zhou

Joint Modeling of Structure Identification and Nuclearity Recognition in Macro Chinese Discourse Treebank (C18-1)

Challenge:	Existing studies on cross-domain sentiment classification ignore the semantic relevance between domains.
Approach:	They propose to use Abstract Meaning Representation to help with cross-domain sentiment classification by combining sentence-level AMRs with text-graph interaction models.
Outcome:	The proposed model is effective over strong baselines and shows its importance over strong models.

Copied to clipboard

Xiaomin Chu, Feng Jiang, Yi Zhou, Guodong Zhou, Qiaoming Zhu

Aspect Sentiment Classification Towards Question-Answering with Reinforced Bidirectional Attention Network (P19-1)

Challenge:	Discourse parsing is a challenging task and plays a critical role in discourse analysis.
Approach:	They propose a macro discourse structure presentation schema to present the macro level discourse structure analysis.
Outcome:	The proposed corpus is based on two tasks of macro discourse structure analysis, including structure identification and nuclearity recognition.

Copied to clipboard

Jingjing Wang, Changlong Sun, Shoushan Li, Xiaozhong Liu, Luo Si, Min Zhang, Guodong Zhou

Style-Aware Contrastive Learning for Multi-Style Image Captioning (2023.findings-eacl)

Challenge:	Existing studies on aspect sentiment classification focus on non-interactive reviews . a new task aims to predict sentiment polarities for specific aspects from interactive reviews based on annotated corpus .
Approach:	They propose a task to predict aspects from interactive QA style reviews using an annotated corpus.
Outcome:	The proposed approach is compared with state-of-the-art methods against a high-quality corpus of data.

Copied to clipboard

Yucheng Zhou, Guodong Long

GLIER: Generative Legal Inference and Evidence Ranking for Legal Case Retrieval (2026.acl-long)

Challenge:	Existing multi-style image captioning methods focus on visual content and style . existing methods overlook the relationship between linguistic style and visual content.
Approach:	They propose a style-aware visual encoder with contrastive learning to mine potential visual content relevant to style and a triplet contrast objective to distinguish whether the image, style and caption matched.
Outcome:	The proposed method achieves state-of-the-art performance and an extensive analysis to verify its effectiveness.

Copied to clipboard

Minghan Li, Tianrui Lv, Chao Zhang, Guodong Zhou

CVAE-based Re-anchoring for Implicit Discourse Relation Classification (2021.findings-emnlp)

Challenge:	Existing dense retrieval methods neglect the explicit legal logic that underpins legal relevance.
Approach:	They propose a framework that reformulates retrieval as an inference process over latent legal variables.
Outcome:	GLIER outperforms strong baselines like SAILER and KELLER in a legal case-based retrieval task . the framework exhibits exceptional data efficiency even when trained with only 10% of the data .

Copied to clipboard

Zujun Dou, Yu Hong, Yu Sun, Guodong Zhou

Text Classification

Challenge:	Existing studies show that training implicit discourse relation classifiers suffers from data sparsity.
Approach:	They propose a re-anchoring strategy to reduce the risk of erroneous sampling . they use Conditional VAE to estimate the risk and migrate the anchor to reduce it .
Outcome:	The proposed method improves the baseline classifier performance on PDTB v2.0 .

Retrieval-Augmented Retrieval: Large Language Models are Strong Zero-Shot Retriever (2024.findings-acl)

Copied to clipboard

Tao Shen, Guodong Long, Xiubo Geng, Chongyang Tao, Yibin Lei, Tianyi Zhou, Michael Blumenstein, Daxin Jiang

Improving AMR Parsing with Sequence-to-Sequence Pre-training (2020.emnlp-main)

Challenge:	Large-scale retrieval is indispensable in information-seeking tasks such as open-domain question answering and knowledgegrounded dialogue.
Approach:	They propose to use a large language model (LLM) to augment a query with its potential answers by prompting LLMs with a composition of the query and the query’s in-domain candidates.
Outcome:	The proposed method breaks brute-force combinations of retrievers with LLMs and lifts the performance of zero-shot retrieval to be very competitive on benchmark datasets.

Copied to clipboard

Dongqin Xu, Junhui Li, Muhua Zhu, Min Zhang, Guodong Zhou

New Compendium of a Myriad of Plants: A New Dataset Describing Ancient Chinese Plants (2026.findings-acl)

Challenge:	Abstract meaning representation (AMR) parsing is limited by the size of curated datasets.
Approach:	They propose a seq2seq pre-training approach to build pre-trained models on three relevant tasks.
Outcome:	The proposed model improves performance on three relevant tasks while maintaining the response of pre-trained models.

Copied to clipboard

Xiaobin Shen, Zhongqing Wang, Shichen Li, Chu-Ren Huang, Guodong Zhou

TopicDiff: A Topic-enriched Diffusion Approach for Multimodal Conversational Emotion Detection (2024.lrec-main)

Challenge:	Existing approaches to digitize ancient Chinese texts and extract information from them are shallow and inconsistent with modern realities.
Approach:	They propose to expand ancient Chinese datasets using large language model . they focus on Great Compendium of Myriad Flowers, an ancient plants dataset .
Outcome:	The proposed model can extract plant-related information from classical Chinese poetry and prose.

Copied to clipboard

Jiamin Luo, Jingjing Wang, Guodong Zhou

Natural Language Interfaces

Challenge:	Existing studies focus on learning contextual information in conversations, neglecting acoustic and vision topic information.
Approach:	They propose a model-agnostic Topic-enriched Diffusion approach for capturing multimodal topic information in MCE tasks.
Outcome:	The proposed approach improves over the state-of-the-art MCE models and the existing models.

One-Teacher and Multiple-Student Knowledge Distillation on Sentiment Classification (2022.coling-1)

Copied to clipboard

Xiaoqin Chang, Sophia Yat Mei Lee, Suyang Zhu, Shoushan Li, Guodong Zhou

Exploring Unified Training Framework for Multimodal User Profiling (2025.coling-main)

Challenge:	Existing knowledge distillation models require large computing resources and long inference time to perform.
Approach:	They propose a one-teacher and multiple-student knowledge distillation approach to distill a deep pre-trained teacher model into multiple shallow student models with ensemble learning.
Outcome:	The proposed method achieves better results with fewer parameters and extremely high speedup ratios on three sentiment classification tasks.

Copied to clipboard

Minjie Qiang, Zhongqing Wang, Shoushan Li, Guodong Zhou

Discourse Parsing Enhanced by Discourse Dependence Perception (2022.aacl-main)

Challenge:	Recent studies on user profiling focus on extracting multiple aspects of user attributes from textual reviews, but these studies do not fully exploit the potential of the rich multimodal data at hand.
Approach:	They propose a task that utilizes both review texts and their accompanying images to generate comprehensive user profiles.
Outcome:	The proposed training framework incorporates historical review texts and images for user profile generation.

Copied to clipboard

Yuqing Xing, Longyin Zhang, Fang Kong, Guodong Zhou

Sentiment Classification towards Question-Answering with Hierarchical Matching Network (D18-1)

Challenge:	Top-down neural models still suffer from the top-down error propagation issue . previous studies gradually switch from feature-based machine learning methods to deep neural models .
Approach:	They propose a top-down framework that learns from discourse dependency and constituency parsing through one shared encoder and two independent decoders.
Outcome:	The proposed framework learns from discourse dependency and constituency parsing through one shared encoder and two independent decoders on a Chinese discourse corpus.

Copied to clipboard

Chenlin Shen, Changlong Sun, Jingjing Wang, Yangyang Kang, Shoushan Li, Xiaozhong Liu, Luo Si, Min Zhang, Guodong Zhou

More than Text: Multi-modal Chinese Word Segmentation (2021.acl-short)

Challenge:	Existing methods to classify QA text contain rich sentiment information.
Approach:	They propose a task/method to address QA sentiment analysis by annotating QA text pair with annotation guidelines.
Outcome:	The proposed method can learn the matching vectors of each Q-sentence, A-sentent unit.

Copied to clipboard

Dong Zhang, Zheng Hu, Shoushan Li, Hanqian Wu, Qiaoming Zhu, Guodong Zhou

Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction (2021.findings-emnlp)

Challenge:	Currently, word segmentation is performed in many languages without word delimiters.
Approach:	They propose to combine the multi-modality to perform Chinese word segmentation . they propose a time-dependent multi-module interactive model to integrate multi-modality information .
Outcome:	The proposed model integrates multi-modal information for word sequence labeling with Chinese language as target . the proposed model performs well on three training sets on Chinese and other languages without word delimiters.

Copied to clipboard

Bo Wang, Tao Shen, Guodong Long, Tianyi Zhou, Yi Chang

Adversarial Attention Modeling for Multi-dimensional Emotion Regression (P19-1)

Challenge:	Aspect-level sentiment classification (ALSC) is a practical setting in aspect-based sentiment analysis due to no opinion term labeling needed, but it fails to interpret why a sentiment polarity is derived for the aspect.
Approach:	They propose a span-based anti-bias aspect representation learning framework that eliminates the sentiment bias in the aspect embedding by adversarial learning against aspects’ prior sentiment.
Outcome:	The proposed framework achieves state-of-the-art performance on five benchmarks, with the capability of unsupervised opinion extraction.

Copied to clipboard

Suyang Zhu, Shoushan Li, Guodong Zhou

Multi-modal Multi-label Emotion Detection with Modality and Label Dependence (2020.emnlp-main)

Challenge:	Empirical evaluation on EMOBANK corpus shows that our approach achieves notable improvements in r-values over the state-of-the-art baselines.
Approach:	They propose a neural network-based approach to multi-dimensional emotion regression which automatically rates multiple emotion dimension scores for an input text.
Outcome:	The proposed approach achieves notable improvements in r-values on both EMOBANK Reader’s and Writer’s multi-dimensional emotion regression tasks over the state-of-the-art baselines.

Copied to clipboard

Dong Zhang, Xincheng Ju, Junhui Li, Shoushan Li, Qiaoming Zhu, Guodong Zhou

A Discrete CVAE for Response Generation on Short-Text Conversation (D19-1)

Challenge:	Existing studies on multi-label emotion detection focus on one modality . current studies focus on label dependence, but there is no consensus on the model .
Approach:	They propose a multi-modal sequence-to-set approach to model label dependence and modality dependence in a multiple-modal scenario.
Outcome:	The proposed approach is able to model the label dependence and the modality dependence in a multi-modal scenario.

Copied to clipboard

Jun Gao, Wei Bi, Xiaojiang Liu, Junhui Li, Guodong Zhou, Shuming Shi

Dialogue Systems & Conversational Agents

Challenge:	Neural conversation models are easy to generate bland and generic responses . however, their improvement of generating high-quality responses is still unsatisfactory .
Approach:	They propose to use a discrete latent variable with an explicit semantic meaning to improve the conditional variational autoencoder on short-text conversation.
Outcome:	The proposed model outperforms various kinds of generation models under automatic and human evaluations and generates more diverse and informative responses.

Enhancing Reasoning Capabilities by Instruction Learning and Chain-of-Thoughts for Implicit Discourse Relation Recognition (2023.findings-emnlp)

Copied to clipboard

Yuxiang Lu, Yu Hong, Zhipang Wang, Guodong Zhou

Reasoning

Challenge:	Existing models for implicit discourse relation recognition are based on generative models, but some studies suggest they do not perform as well as generic encoder-only models for NLU tasks.
Approach:	They propose a classification method that is solely based on generative models and utilize Chain-of-Thoughts to partition the inference process into a sequence of three successive stages.
Outcome:	The proposed model outperforms existing models on a natural language understanding task.

Towards Robust Ranker for Text Retrieval (2023.findings-acl)

Copied to clipboard

Yucheng Zhou, Tao Shen, Xiubo Geng, Chongyang Tao, Can Xu, Guodong Long, Binxing Jiao, Daxin Jiang

Interactively-Propagative Attention Learning for Implicit Discourse Relation Recognition (2020.coling-main)

Challenge:	Existing methods for text retrieval are based on a 'retrieval & rerank' pipeline, which uses a fast retriever to fetch a set of top document candidates, while a robust ranker is based upon a weak negative mining during contrastive learning.
Approach:	They propose a multi-adversarial training strategy that leverages multiple retrievers as generators to challenge a ranker.
Outcome:	The proposed model outperforms the existing de facto ranker training paradigms on the passage retrieval benchmarks using BM25-reranking, full-ranking and retriever distillation.

Copied to clipboard

Huibin Ruan, Yu Hong, Yang Xu, Zhen Huang, Guodong Zhou, Min Zhang

Challenge:	Existing models for discourse relation recognition use self-attention and interactive-attention mechanisms.
Approach:	They develop a propagative attention learning model using a cross-coupled two-channel network.
Outcome:	The proposed model improves on the baseline models on a Penn Discourse Treebank.

Human-Like Decision Making: Document-level Aspect Sentiment Classification via Hierarchical Reinforcement Learning (D19-1)

Copied to clipboard

Jingjing Wang, Changlong Sun, Shoushan Li, Jiancheng Wang, Luo Si, Min Zhang, Xiaozhong Liu, Guodong Zhou

XLPT-AMR: Cross-Lingual Pre-Training via Multi-Task Learning for Zero-Shot AMR Parsing and Text Generation (2021.acl-long)

Challenge:	Recent neural networks have shown promising results on Document-level Aspect Sentiment Classification (DASC) however, these approaches often offer little transparency w.r.t. their inner working mechanisms and lack interpretability.
Approach:	They propose a Hierarchical Reinforcement Learning approach to DASC that incorporates clause selection and word selection strategies to tackle the data noise problem.
Outcome:	The proposed approach over the state-of-the-art approaches shows impressive performance over the current baselines.

Copied to clipboard

Dongqin Xu, Junhui Li, Muhua Zhu, Min Zhang, Guodong Zhou

Coupling Context Modeling with Zero Pronoun Recovering for Document-Level Natural Language Generation (2021.emnlp-main)

Challenge:	Abstract Meaning Representation (AMR) research is limited and challenging for languages other than English.
Approach:	They propose a cross-lingual pre-training approach for AMR parsing and text generation . they use an English-to-English parallel dataset and a multi-task learning approach .
Outcome:	The proposed approach outperforms baseline pre-training methods on English parsing and text generation tasks.

Copied to clipboard

Xin Tan, Longyin Zhang, Guodong Zhou

Text Generation

Challenge:	ZP-annotated natural language generation (NLG) corpora are scarce in pro-drop languages . despite efforts to bridge the discrepancy between human and machine, zero pronouns still persist in pro -drop tasks.
Approach:	They propose a highly adaptive two-stage approach to couple context modeling with ZP recovering to mitigate the ZP problem in NLG tasks.
Outcome:	The proposed approach can improve translation, question answering, and summarization tasks.

Stance Detection with Hierarchical Attention Network (C18-1)

Copied to clipboard

Qingying Sun, Zhongqing Wang, Qiaoming Zhu, Guodong Zhou